{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.8181818181818183,
  "eval_steps": 500,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.09090909090909091,
      "grad_norm": 13.637824058532715,
      "learning_rate": 2.8000000000000003e-05,
      "loss": 10.2163,
      "step": 10
    },
    {
      "epoch": 0.18181818181818182,
      "grad_norm": 17.454669952392578,
      "learning_rate": 6.800000000000001e-05,
      "loss": 7.5797,
      "step": 20
    },
    {
      "epoch": 0.2727272727272727,
      "grad_norm": 0.6968994140625,
      "learning_rate": 0.00010800000000000001,
      "loss": 1.2082,
      "step": 30
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 0.28175318241119385,
      "learning_rate": 0.000148,
      "loss": 0.6546,
      "step": 40
    },
    {
      "epoch": 0.45454545454545453,
      "grad_norm": 0.3333212435245514,
      "learning_rate": 0.000188,
      "loss": 0.5694,
      "step": 50
    },
    {
      "epoch": 0.5454545454545454,
      "grad_norm": 0.29647210240364075,
      "learning_rate": 0.000195,
      "loss": 0.5511,
      "step": 60
    },
    {
      "epoch": 0.6363636363636364,
      "grad_norm": 0.3127809762954712,
      "learning_rate": 0.00018785714285714288,
      "loss": 0.5503,
      "step": 70
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 0.32088786363601685,
      "learning_rate": 0.00018071428571428573,
      "loss": 0.4812,
      "step": 80
    },
    {
      "epoch": 0.8181818181818182,
      "grad_norm": 0.3519816994667053,
      "learning_rate": 0.00017357142857142859,
      "loss": 0.503,
      "step": 90
    },
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 0.36626359820365906,
      "learning_rate": 0.00016642857142857144,
      "loss": 0.5028,
      "step": 100
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.32065916061401367,
      "learning_rate": 0.0001592857142857143,
      "loss": 0.4697,
      "step": 110
    },
    {
      "epoch": 1.0909090909090908,
      "grad_norm": 0.39233624935150146,
      "learning_rate": 0.00015214285714285715,
      "loss": 0.4678,
      "step": 120
    },
    {
      "epoch": 1.1818181818181819,
      "grad_norm": 0.35013166069984436,
      "learning_rate": 0.000145,
      "loss": 0.4484,
      "step": 130
    },
    {
      "epoch": 1.2727272727272727,
      "grad_norm": 0.3643708825111389,
      "learning_rate": 0.00013785714285714285,
      "loss": 0.4111,
      "step": 140
    },
    {
      "epoch": 1.3636363636363638,
      "grad_norm": 0.37518009543418884,
      "learning_rate": 0.00013071428571428574,
      "loss": 0.4293,
      "step": 150
    },
    {
      "epoch": 1.4545454545454546,
      "grad_norm": 0.3919459283351898,
      "learning_rate": 0.0001235714285714286,
      "loss": 0.4041,
      "step": 160
    },
    {
      "epoch": 1.5454545454545454,
      "grad_norm": 0.36627262830734253,
      "learning_rate": 0.00011642857142857144,
      "loss": 0.4226,
      "step": 170
    },
    {
      "epoch": 1.6363636363636362,
      "grad_norm": 0.38178035616874695,
      "learning_rate": 0.00010928571428571428,
      "loss": 0.453,
      "step": 180
    },
    {
      "epoch": 1.7272727272727273,
      "grad_norm": 0.34095773100852966,
      "learning_rate": 0.00010214285714285714,
      "loss": 0.4492,
      "step": 190
    },
    {
      "epoch": 1.8181818181818183,
      "grad_norm": 0.4153459966182709,
      "learning_rate": 9.5e-05,
      "loss": 0.4594,
      "step": 200
    }
  ],
  "logging_steps": 10,
  "max_steps": 330,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 8958709963161600.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}